© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195620
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Less
    0.44
    擺
    0.40
    Marsh
    0.39
    LESS
    0.38
    lebih
    0.38
    Proced
    0.37
    浒
    0.37
    Gift
    0.37
    more
    0.37
    Pray
    0.37
    POSITIVE LOGITS
     formats
    0.41
     dedication
    0.41
     industry
    0.40
     strength
    0.40
     freedom
    0.39
     flexibility
    0.39
     openness
    0.39
     transparency
    0.39
     ವಿವರ
    0.39
     <?=
    0.38
    Activations Density 0.009%

    No Known Activations